[PATCH 04/10] drm/amdgpu: add gfx11 emit shadow callback

[Alex Deucher]

From: Christian König <christian.koenig at amd.com>

Add ring callback for gfx to update the CP firmware
with the new shadow information before we process the
IB.

v2: add implementation for new packet (Alex)
v3: add current FW version checks (Alex)
v4: only initialize shadow on first use
    Only set IB_VMID when a valid shadow buffer is present
    (Alex)

Signed-off-by: Christian König <christian.koenig at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h |  2 ++
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c  | 46 +++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/nvd.h        |  5 ++-
 3 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index de9e7a00bb15..4ad9e225d6e6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -364,6 +364,8 @@ struct amdgpu_gfx {
 
 	struct amdgpu_ring		sw_gfx_ring[AMDGPU_MAX_SW_GFX_RINGS];
 	struct amdgpu_ring_mux          muxer;
+
+	bool				cp_gfx_shadow; /* for gfx11 */
 };
 
 #define amdgpu_gfx_get_gpu_clock_counter(adev) (adev)->gfx.funcs->get_gpu_clock_counter((adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 3bf697a80cf2..166a3f640042 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -463,6 +463,27 @@ static int gfx_v11_0_init_toc_microcode(struct amdgpu_device *adev, const char *
 	return err;
 }
 
+static void gfx_v11_0_check_fw_cp_gfx_shadow(struct amdgpu_device *adev)
+{
+	switch (adev->ip_versions[GC_HWIP][0]) {
+	case IP_VERSION(11, 0, 0):
+	case IP_VERSION(11, 0, 2):
+	case IP_VERSION(11, 0, 3):
+		/* XXX fix me! */
+		if ((adev->gfx.me_fw_version >= 1498) &&
+		    (adev->gfx.me_feature_version >= 29) &&
+		    (adev->gfx.pfp_fw_version >= 1541) &&
+		    (adev->gfx.pfp_feature_version >= 29) &&
+		    (adev->gfx.mec_fw_version >= 507) &&
+		    (adev->gfx.mec_feature_version >= 29))
+			adev->gfx.cp_gfx_shadow = true;
+		break;
+	default:
+		adev->gfx.cp_gfx_shadow = false;
+		break;
+	}
+}
+
 static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 {
 	char fw_name[40];
@@ -539,6 +560,7 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 	/* only one MEC for gfx 11.0.0. */
 	adev->gfx.mec2_fw = NULL;
 
+	gfx_v11_0_check_fw_cp_gfx_shadow(adev);
 out:
 	if (err) {
 		amdgpu_ucode_release(&adev->gfx.pfp_fw);
@@ -5563,6 +5585,28 @@ static void gfx_v11_0_ring_emit_cntxcntl(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, 0);
 }
 
+static void gfx_v11_0_ring_emit_gfx_shadow(struct amdgpu_ring *ring,
+					   struct amdgpu_job *job)
+{
+	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
+	struct amdgpu_device *adev = ring->adev;
+
+	if (!adev->gfx.cp_gfx_shadow)
+		return;
+
+	amdgpu_ring_write(ring, PACKET3(PACKET3_SET_Q_PREEMPTION_MODE, 7));
+	amdgpu_ring_write(ring, lower_32_bits(job->shadow_va));
+	amdgpu_ring_write(ring, upper_32_bits(job->shadow_va));
+	amdgpu_ring_write(ring, lower_32_bits(job->gds_va));
+	amdgpu_ring_write(ring, upper_32_bits(job->gds_va));
+	amdgpu_ring_write(ring, lower_32_bits(job->csa_va));
+	amdgpu_ring_write(ring, upper_32_bits(job->csa_va));
+	amdgpu_ring_write(ring, job->shadow_va ?
+			  PACKET3_SET_Q_PREEMPTION_MODE_IB_VMID(vmid) : 0);
+	amdgpu_ring_write(ring, job->init_shadow ?
+			  PACKET3_SET_Q_PREEMPTION_MODE_INIT_SHADOW_MEM : 0);
+}
+
 static unsigned gfx_v11_0_ring_emit_init_cond_exec(struct amdgpu_ring *ring)
 {
 	unsigned ret;
@@ -6183,6 +6227,7 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_gfx = {
 	.set_wptr = gfx_v11_0_ring_set_wptr_gfx,
 	.emit_frame_size = /* totally 242 maximum if 16 IBs */
 		5 + /* COND_EXEC */
+		9 + /* SET_Q_PREEMPTION_MODE */
 		7 + /* PIPELINE_SYNC */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
@@ -6209,6 +6254,7 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_gfx = {
 	.insert_nop = amdgpu_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.emit_cntxcntl = gfx_v11_0_ring_emit_cntxcntl,
+	.emit_gfx_shadow = gfx_v11_0_ring_emit_gfx_shadow,
 	.init_cond_exec = gfx_v11_0_ring_emit_init_cond_exec,
 	.patch_cond_exec = gfx_v11_0_ring_emit_patch_cond_exec,
 	.preempt_ib = gfx_v11_0_ring_preempt_ib,
diff --git a/drivers/gpu/drm/amd/amdgpu/nvd.h b/drivers/gpu/drm/amd/amdgpu/nvd.h
index fd6b58243b03..631dafb92299 100644
--- a/drivers/gpu/drm/amd/amdgpu/nvd.h
+++ b/drivers/gpu/drm/amd/amdgpu/nvd.h
@@ -462,6 +462,9 @@
 #              define PACKET3_QUERY_STATUS_ENG_SEL(x)          ((x) << 25)
 #define	PACKET3_RUN_LIST				0xA5
 #define	PACKET3_MAP_PROCESS_VM				0xA6
-
+/* GFX11 */
+#define	PACKET3_SET_Q_PREEMPTION_MODE			0xF0
+#              define PACKET3_SET_Q_PREEMPTION_MODE_IB_VMID(x)  ((x) << 0)
+#              define PACKET3_SET_Q_PREEMPTION_MODE_INIT_SHADOW_MEM    (1 << 0)
 
 #endif
-- 
2.39.2